Motion learning and adaptive impedance for robot control during physical interaction with humans

Abstract

Abstract-This article combines programming by demonstration and adaptive control for teaching a robot to physically interact with a human in a collaborative task requiring sharing of a load by the two partners. Learning a task model allows the robot to anticipate the partner's intentions and adapt its motion according to perceived forces. As the human represents a highly complex contact environment, direct reproduction of the learned model may lead to sub-optimal results. To compensate for unmodelled uncertainties, in addition to learning we propose an adaptive control algorithm that tunes the impedance parameters, so as to ensure accurate reproduction. To facilitate the illustration of the concepts introduced in this paper and provide a systematic evaluation, we present experimental results obtained with simulation of a dyad of two planar 2-DOF robots.

A User Study on Kinesthetic Teaching of Redundant Robots in Task and Configuration Space

“…An advanced interaction concept allows iterative refinement of motion primitives subsequent to observational learning of a reference trajectory. Another example of motion learning and adaptation through kinesthetic teaching combines imitation learning and an adaptive control algorithm (Gribovskaya, Kheddar, & Billard, 2011), facilitating adaptive impedance control of robot motions in human-robot collaboration scenarios. Ito and Tani (2004) present a related approach based on online imitation learning inspired by the idea of mirror neurons.…”

Online kinematics estimation for active human-robot manipulation of jointly held objects

“…In this framework, confidence measures have been exploited to enable automatic switching of roles [12]. Other works combine motion learning to allow the robot to anticipate the human partner's impedance with adaptive control to compensate for unmodelled uncertainties in the human part of the system [13] and understanding of human behavior when the robot is the leader [14].…”

Analysis of Rigid Extended Object Co-Manipulation by Human Dyads: Lateral Movement Characterization

“…While this model has been shown to be useful for Cartesian movements, [10], [11], it does not generalize to extended objects due to the rotation-translation problem, nor does it address rotational movements alone. Other proposed models for co-manipulation include programming by demonstration (PBD) [12], [13], finite state machines (FSM) [3], [2], uncertainty control [14], and movement coordination [15]. PBD involves some pre-programmed information, and does not easily generalize to a case where a new, unlearned motion is required.…”